works on

From the 1 of 6 linked papers with an AI index.

collaborators

6 papers

math.AG2026

An atomic criterion for irrationality without quantum computations

Vladimiro Benedetti, Aideen Fay, Jérémy Guéré +2

The paper presents a cohomological criterion that proves irrationality of certain algebraic varieties without computing quantum atoms, using monodromy equivariance and irreducibili…

math.AG2026

The Very General Verra Fourfold is Irrational

Aideen Fay

We show that the very general Verra fourfold is irrational, using the Hodge atom framework of Katzarkov--Kontsevich--Pantev--Yu. Two novel points are: a refined analysis of Hodge a…

math.AG2026

Equivariant irrationality of very general symmetric Verra fourfolds

Aideen Fay

We prove that a very general complex symmetric Verra fourfold is not \(\ZZ/2\)-birational to \(\PP^4\), using the \emph{theory of atoms} introduced by Katzarkov--Kontsevich--Pantev…

cs.LG2026

The Shape of Adversarial Influence: Characterizing LLM Latent Spaces with Persistent Homology

Aideen Fay, Inés García-Redondo, Qiquan Wang +2

Existing interpretability methods for Large Language Models (LLMs) predominantly capture linear directions or isolated features. This overlooks the high-dimensional, relational, an…

cs.CR2025

LLMail-Inject: A Dataset from a Realistic Adaptive Prompt Injection Challenge

Sahar Abdelnabi, Aideen Fay, Ahmed Salem +22

Indirect Prompt Injection attacks exploit the inherent limitation of Large Language Models (LLMs) to distinguish between instructions and data in their inputs. Despite numerous def…

cs.CR2025

Get my drift? Catching LLM Task Drift with Activation Deltas

Sahar Abdelnabi, Aideen Fay, Giovanni Cherubin +3

LLMs are commonly used in retrieval-augmented applications to execute user instructions based on data from external sources. For example, modern search engines use LLMs to answer q…